Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1783 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9863. Min Range: -5.9863
Max Act: 5.9863. Min Act: -0.1700
Data Index: 3755406 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9863. Min Range: -5.9863
Max Act: 5.8301. Min Act: -0.1700
Data Index: 3105301 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9863. Min Range: -5.9863
Max Act: 5.8301. Min Act: -0.1700
Data Index: 3745085 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9863. Min Range: -5.9863
Max Act: 5.6738. Min Act: -0.1700
Data Index: 18095 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9863. Min Range: -5.9863
Max Act: 5.6738. Min Act: -0.1700
Data Index: 2192639 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9863. Min Range: -5.9863
Max Act: 5.7051. Min Act: -0.1700
Data Index: 6992662 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9863. Min Range: -5.9863
Max Act: 5.6113. Min Act: -0.1700
Data Index: 7045692 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9863. Min Range: -5.9863
Max Act: 5.6426. Min Act: -0.1700
Data Index: 4307501 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9863. Min Range: -5.9863
Max Act: 5.6113. Min Act: -0.1700
Data Index: 5412054 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9863. Min Range: -5.9863
Max Act: 5.5801. Min Act: -0.1700
Data Index: 4106989 (Open Web Text)
Max Activating Token Index: 551
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9863. Min Range: -5.9863
Max Act: 5.5176. Min Act: -0.1700
Data Index: 451471 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9863. Min Range: -5.9863
Max Act: 5.5176. Min Act: -0.1700
Data Index: 1609584 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9863. Min Range: -5.9863
Max Act: 5.4863. Min Act: -0.1700
Data Index: 4476603 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9863. Min Range: -5.9863
Max Act: 5.4863. Min Act: -0.1700
Data Index: 3233326 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9863. Min Range: -5.9863
Max Act: 5.4863. Min Act: -0.1700
Data Index: 7107144 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9863. Min Range: -5.9863
Max Act: 5.4551. Min Act: -0.1700
Data Index: 2192454 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9863. Min Range: -5.9863
Max Act: 5.4551. Min Act: -0.1700
Data Index: 7107135 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9863. Min Range: -5.9863
Max Act: 5.4238. Min Act: -0.1700
Data Index: 5065475 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9863. Min Range: -5.9863
Max Act: 5.3926. Min Act: -0.1700
Data Index: 1582216 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9863. Min Range: -5.9863
Max Act: 5.3926. Min Act: -0.1700
Data Index: 7763561 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #19